Concept-aware clustering for decentralized deep learning under temporal shift
Not on the map. Why?
Abstract (arXiv)
Decentralized deep learning requires dealing with non-iid data across clients, which may also change over time due to temporal shifts. While non-iid data has been extensively studied in distributed settings, temporal shifts have received no attention. To the best of our knowledge, we are first with tackling the novel and challenging problem of decentralized learning with non-iid and dynamic data. We propose a novel algorithm that can automatically discover and adapt to the evolving concepts in the network, without any prior knowledge or estimation of the number of concepts. We evaluate our algorithm on standard benchmark datasets and demonstrate that it outperforms previous methods for decentralized learning.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 19 references that are in the map. First posted on arXiv 22 Jun 2023.
Builds on
9 of 19 references.
References · 9
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2017Deeper, Broader and Artier Domain Generalizationcited by 986
- 2020An Efficient Framework for Clustered Federated Learningcited by 511
- 2019Federated Machine Learning: Concept and Applicationscited by 412
- 2022Federated Learning under Distributed Concept Driftcited by 36
- 2016Gossip training for deep learningcited by 35
- 2021Decentralized federated learning of deep neural networks on non-iid datacited by 25
- 2022Decentralized adaptive clustering of deep nets is beneficial for client collaborationcited by 7
Built on by
Not cited yet.